© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 45658
    Prev
    Next
    INDEX
    Explanations

    words followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is highly specialized to fire on the word “with.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     while
    -1.05
     almost
    -0.96
     their
    -0.91
     While
    -0.85
     even
    -0.84
    “……
    -0.82
     strongly
    -0.82
    Далее
    -0.82
     through
    -0.82
     just
    -0.82
    POSITIVE LOGITS
     gas
    1.05
    ガス
    1.01
    BJP
    0.92
    Gas
    0.92
    KOV
    0.86
    eynman
    0.85
    })
    0.85
    0.84
    argest
    0.83
     charset
    0.82
    Activations Density 0.000%

    No Known Activations